{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LNI3PTCQGH5MXH5Q2ZWG23NC6S","short_pith_number":"pith:LNI3PTCQ","schema_version":"1.0","canonical_sha256":"5b51b7cc5031facb9fb0d66c6d6da2f4b98854ed01928ce9cf6fa43f9d4cdd36","source":{"kind":"arxiv","id":"2312.17235","version":3},"attestation_state":"computed","paper":{"title":"A Simple LLM Framework for Long-Range Video Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Gedas Bertasius, Md Mohaiminul Islam, Mohit Bansal, Shoubin Yu, Taixi Lu, Ziyang Wang","submitted_at":"2023-12-28T18:58:01Z","abstract_excerpt":"We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory queues, state-space layers, etc.), our approach uses a frame/clip-level visual captioner (e.g., BLIP2, LaViLa, LLaVA) coupled with a Large Language Model (GPT-3.5, GPT-4) leading to a simple yet surprisingly effective LVQA framework. Specifically, we decompose short and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual ca"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.17235","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T18:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"62fc8759ee839aeaf29915dc5b3cc167fe80cbafa3c41ffb2b89c05b77105e4e","abstract_canon_sha256":"1a0114bf89dc9fcb2c9c81ebb242ed3ae99f956d139fef712c53956f559ba021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:22.123777Z","signature_b64":"HnNz8RWJi9ekkVcmkDSBoXLnEr1aaXnyCUOaDxyOWM4bamkRZK2keg4i7vvTQ/0CgixpQyBxhnCcKvxqI4jcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b51b7cc5031facb9fb0d66c6d6da2f4b98854ed01928ce9cf6fa43f9d4cdd36","last_reissued_at":"2026-07-05T09:18:22.123276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:22.123276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple LLM Framework for Long-Range Video Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Gedas Bertasius, Md Mohaiminul Islam, Mohit Bansal, Shoubin Yu, Taixi Lu, Ziyang Wang","submitted_at":"2023-12-28T18:58:01Z","abstract_excerpt":"We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory queues, state-space layers, etc.), our approach uses a frame/clip-level visual captioner (e.g., BLIP2, LaViLa, LLaVA) coupled with a Large Language Model (GPT-3.5, GPT-4) leading to a simple yet surprisingly effective LVQA framework. Specifically, we decompose short and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17235","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.17235/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.17235","created_at":"2026-07-05T09:18:22.123334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17235v3","created_at":"2026-07-05T09:18:22.123334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17235","created_at":"2026-07-05T09:18:22.123334+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNI3PTCQGH5M","created_at":"2026-07-05T09:18:22.123334+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNI3PTCQGH5MXH5Q","created_at":"2026-07-05T09:18:22.123334+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNI3PTCQ","created_at":"2026-07-05T09:18:22.123334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05748","citing_title":"UNIVID: Unified Vision-Language Model for Video Moderation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29472","citing_title":"Agent-Computer Observation Interfaces Enable Dynamic Computer Use","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24943","citing_title":"Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11113","citing_title":"VIDEOP2R: Video Understanding from Perception to Reasoning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16994","citing_title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02891","citing_title":"Progressive Video Condensation with MLLM Agent for Long-form Video Understanding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23145","citing_title":"UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S","json":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S.json","graph_json":"https://pith.science/api/pith-number/LNI3PTCQGH5MXH5Q2ZWG23NC6S/graph.json","events_json":"https://pith.science/api/pith-number/LNI3PTCQGH5MXH5Q2ZWG23NC6S/events.json","paper":"https://pith.science/paper/LNI3PTCQ"},"agent_actions":{"view_html":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S","download_json":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S.json","view_paper":"https://pith.science/paper/LNI3PTCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17235&json=true","fetch_graph":"https://pith.science/api/pith-number/LNI3PTCQGH5MXH5Q2ZWG23NC6S/graph.json","fetch_events":"https://pith.science/api/pith-number/LNI3PTCQGH5MXH5Q2ZWG23NC6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S/action/storage_attestation","attest_author":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S/action/author_attestation","sign_citation":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S/action/citation_signature","submit_replication":"https://pith.science/pith/LNI3PTCQGH5MXH5Q2ZWG23NC6S/action/replication_record"}},"created_at":"2026-07-05T09:18:22.123334+00:00","updated_at":"2026-07-05T09:18:22.123334+00:00"}